{"total":116,"rows":[{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306,"area":"agents"},{"id":"2503.18666","title":"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","created":"2025-03-24","cited_by_count":223,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2507.06134","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","created":"2025-07-08","cited_by_count":75,"area":"agents"},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"id":"2506.14697","title":"AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions","created":"2025-06-17","cited_by_count":38,"area":"mllm"},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2510.09781","title":"Building a Foundational Guardrail for General Agentic Systems via Synthetic Data","created":"2025-10-10","cited_by_count":29,"area":"agents"},{"id":"2508.00500","title":"ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction","created":"2025-08-01","cited_by_count":28,"area":"agents"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2503.15707","title":"Safety Aware Task Planning via Large Language Models in Robotics","created":"2025-03-19","cited_by_count":24,"area":"lr"},{"id":"2505.19933","title":"Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making","created":"2025-05-26","cited_by_count":20,"area":null},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2509.25885","title":"SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents","created":"2025-09-30","cited_by_count":17,"area":"agents"},{"id":"2604.01438","title":"ClawSafety: \"Safe\" LLMs, Unsafe Agents","created":"2026-04-01","cited_by_count":17,"area":"agents"},{"id":"2505.23559","title":"SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents","created":"2025-05-29","cited_by_count":16,"area":"agents"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2512.21220","title":"RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic","created":"2025-12-24","cited_by_count":14,"area":"agents"},{"id":"2604.16968","title":"On Safety Risks in Experience-Driven Self-Evolving Agents","created":"2026-04-18","cited_by_count":14,"area":"agents"},{"id":"2504.15699","title":"Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation","created":"2025-04-22","cited_by_count":13,"area":"agents"},{"id":"2604.23775","title":"Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms","created":"2026-04-26","cited_by_count":13,"area":"vla"},{"id":"2507.08270","title":"Agent Safety Alignment via Reinforcement Learning","created":"2025-07-11","cited_by_count":11,"area":"agents"},{"id":"2502.15086","title":"Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models","created":"2025-02-20","cited_by_count":10,"area":"safety"},{"id":"2508.05855","title":"Safety of Embodied Navigation: A Survey","created":"2025-08-07","cited_by_count":10,"area":null},{"id":"2606.26524","title":"VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills","created":"2026-06-25","cited_by_count":9,"area":"agents"},{"id":"2508.00935","title":"Measuring Harmfulness of Computer-Using Agents","created":"2025-07-31","cited_by_count":8,"area":"agents"},{"id":"2602.11749","title":"AIR: Improving Agent Safety through Incident Response","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2604.12447","title":"HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models","created":"2026-04-14","cited_by_count":8,"area":"vla"},{"id":"2504.14773","title":"PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities","created":"2025-04-21","cited_by_count":7,"area":"agents"},{"id":"2505.10872","title":"REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?","created":"2025-05-16","cited_by_count":7,"area":"agents"},{"id":"2601.22136","title":"StepShield: When, Not Whether to Intervene on Rogue Agents","created":"2026-01-29","cited_by_count":7,"area":"safety"},{"id":"2605.02900","title":"Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses","created":"2026-03-28","cited_by_count":7,"area":"safety"},{"id":"2606.10749","title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","created":"2026-06-09","cited_by_count":7,"area":"agents"},{"id":"2505.17735","title":"SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator","created":"2025-05-23","cited_by_count":6,"area":"agents"},{"id":"2511.21460","title":"MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning","created":"2025-11-26","cited_by_count":6,"area":"agents"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2603.28807","title":"SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants","created":"2026-03-28","cited_by_count":6,"area":"agents"},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2509.00117","title":"Embodied AI: Emerging Risks and Opportunities for Policy Action","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2509.23690","title":"HomeSafeBench: Benchmarking Embodied Vision-Language Models in Free-Exploration Home Safety Inspection","created":"2025-09-28","cited_by_count":5,"area":"mllm"},{"id":"2603.14367","title":"HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task","created":"2026-03-15","cited_by_count":5,"area":"mllm"},{"id":"2604.18463","title":"Using large language models for embodied planning introduces systematic safety risks","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2509.23694","title":"SafeSearch: Automated Red-Teaming of LLM-Based Search Agents","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2603.19092","title":"SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues","created":"2026-03-19","cited_by_count":4,"area":"mllm"},{"id":"2603.25747","title":"BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments","created":"2026-01-30","cited_by_count":4,"area":"agents"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.20544","title":"The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents","created":"2026-05-19","cited_by_count":4,"area":"mllm"},{"id":"2605.28214","title":"Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2508.01554","title":"Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models","created":"2025-08-03","cited_by_count":3,"area":null},{"id":"2509.03383","title":"ANNIE: Be Careful of Your Robots","created":"2025-09-03","cited_by_count":3,"area":"vla"},{"id":"2602.14135","title":"ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI","created":"2026-02-15","cited_by_count":3,"area":null},{"id":"2603.11987","title":"LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories","created":"2026-03-12","cited_by_count":3,"area":"lr"},{"id":"2605.30924","title":"EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents","created":"2026-05-29","cited_by_count":3,"area":"agents"},{"id":"2606.22673","title":"AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent","created":"2026-06-21","cited_by_count":3,"area":"agents"},{"id":"2510.12985","title":"SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents","created":"2025-10-14","cited_by_count":2,"area":"agents"},{"id":"2604.11174","title":"EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2605.19328","title":"RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents","created":"2026-05-19","cited_by_count":2,"area":"mllm"},{"id":"2606.04051","title":"RUBAS: Rubric-Based Reinforcement Learning for Agent Safety","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.31045","title":"LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2607.14543","title":"SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents","created":"2026-07-16","cited_by_count":2,"area":"mllm"},{"id":"2609.00028","title":"UI-Venus-2 Technical Report","created":"2026-08-27","cited_by_count":2,"area":"agents"},{"id":"2510.21524","title":"EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law","created":"2025-10-24","cited_by_count":1,"area":"agents"},{"id":"2511.03001","title":"Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.19016","title":"DREAM: Dynamic Red-teaming across Environments for AI Models","created":"2025-12-22","cited_by_count":1,"area":"agents"},{"id":"2602.16902","title":"LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.11975","title":"HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios","created":"2026-03-12","cited_by_count":1,"area":"mllm"},{"id":"2604.19638","title":"SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models","created":"2026-04-21","cited_by_count":1,"area":"mllm"},{"id":"2604.26577","title":"Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.20641","title":"Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs","created":"2026-05-20","cited_by_count":1,"area":"safety"},{"id":"2606.04037","title":"Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.05660","title":"Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.12207","title":"Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.31073","title":"MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.00218","title":"EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2607.16247","title":"Self-Evolving Just-In-Time Memory for Proactive Embodied Safety","created":"2026-06-26","cited_by_count":1,"area":"mllm"},{"id":"2608.02683","title":"$S^3$: Improving Agent Safety through Multi-Stage Defense","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2511.18114","title":"ASTRA: Agentic Steerability and Risk Assessment Framework","created":"2025-11-22","cited_by_count":0,"area":"agents"},{"id":"2601.05529","title":"Before We Trust Them: Decision-Making Failures in Navigation of Foundation Models","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2602.01644","title":"From Perception to Action: Spatial AI Agents and World Models","created":"2026-02-02","cited_by_count":0,"area":"wm"},{"id":"2603.09157","title":"Real-Time Trust Verification for Safe Agentic Actions using TrustBench","created":"2026-03-10","cited_by_count":0,"area":"agents"},{"id":"2603.29759","title":"TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2604.16405","title":"ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models","created":"2026-03-31","cited_by_count":0,"area":"wm"},{"id":"2605.05340","title":"How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study","created":"2026-05-06","cited_by_count":0,"area":"mllm"},{"id":"2605.06992","title":"Why Does Agentic Safety Fail to Generalize Across Tasks?","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.09387","title":"NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.10386","title":"GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic","created":"2026-05-11","cited_by_count":0,"area":"driving"},{"id":"2605.31196","title":"Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.13994","title":"Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2606.23927","title":"RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems","created":"2026-06-22","cited_by_count":0,"area":"agents"},{"id":"2607.15218","title":"When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space","created":"2026-07-16","cited_by_count":0,"area":"safety"},{"id":"2607.18062","title":"UniETP: Unifying Environments for Generalizable Embodied Task Planning","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.19729","title":"SafeBranch: Branch-Pair Safety Alignment for Embodied Agents","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.21928","title":"GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.22232","title":"Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language Models","created":"2026-08-23","cited_by_count":0,"area":"mllm"},{"id":"2608.23839","title":"Resilience Matters for Embodied Agents System: New Metrics, Systematic Evaluation, and Optimization","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.28300","title":"MaCoPlanner: LLM-Assisted Manual-Compiled Task Planning with Proactive Safety Verification for Robotic Industrial Panel Operation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.28305","title":"PanelShield: Verifiable Closed-Loop Safe Planning for Robotic Industrial Panel Operation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.08444","title":"Safe Task Planning with Long-Term Graph Memory for Embodied Agents","created":"2026-09-08","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}